Training in progress, step 10000, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +766 -2
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738367848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb9f3b8a1efbafead71f0b4f3c0934de3258af1a9bfad9aecc866f7dc032377f
|
| 3 |
size 738367848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1476823354
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:090bb424ceafc5d15809a08a16a11eb78b1ac54f4b1366d08eb4391ce4040896
|
| 3 |
size 1476823354
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c383f9e8151a96a9b2b8c275978c19aa387d72a92b0fa7ffae9836fb29ad4e1
|
| 3 |
size 15984
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68bb140caa20e97fbacbd7b5bfac9f50a34da20ffb8898607809de5338939b7
|
| 3 |
size 15984
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84b2b03148e735c06e96e9718897d377bb259c4fc8d0d7eac4359e0df9fd59c3
|
| 3 |
size 15984
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb82703e57f841f914dfb29dc3442d88d2c174cf8ce56f91f0c9c5f2849c5754
|
| 3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d69503f206ccaaa32432817fe07a0b2fe6f226f63d9d38c4bb47f2804049c1
|
| 3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e0fdfa3710c3ff050391030ae78220221b31a31e2ceea64687f7a428110d141
|
| 3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a7b71b6ee08059a6838f5a634279837dec0a6f331500089354f5a30e88cd0b0
|
| 3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b12210119d32a8e51c4b367e898fd3bee7de6dc9d70f1258ce5df806569ea8a4
|
| 3 |
size 15984
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cc7c9d1278bb28457a3d5ee38d783399f75651e4b34a536f0367d5f3082f3b4
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -6883,6 +6883,770 @@
|
|
| 6883 |
"eval_spearman_manhattan": 0.7319318616566108,
|
| 6884 |
"eval_steps_per_second": 7.274,
|
| 6885 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6886 |
}
|
| 6887 |
],
|
| 6888 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.372071227741332,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 6883 |
"eval_spearman_manhattan": 0.7319318616566108,
|
| 6884 |
"eval_steps_per_second": 7.274,
|
| 6885 |
"step": 9000
|
| 6886 |
+
},
|
| 6887 |
+
{
|
| 6888 |
+
"epoch": 8.44423617619494,
|
| 6889 |
+
"grad_norm": 0.6332679986953735,
|
| 6890 |
+
"learning_rate": 9.934030370923575e-06,
|
| 6891 |
+
"loss": 0.027,
|
| 6892 |
+
"step": 9010
|
| 6893 |
+
},
|
| 6894 |
+
{
|
| 6895 |
+
"epoch": 8.45360824742268,
|
| 6896 |
+
"grad_norm": 0.6109747886657715,
|
| 6897 |
+
"learning_rate": 9.933957152689306e-06,
|
| 6898 |
+
"loss": 0.0242,
|
| 6899 |
+
"step": 9020
|
| 6900 |
+
},
|
| 6901 |
+
{
|
| 6902 |
+
"epoch": 8.462980318650422,
|
| 6903 |
+
"grad_norm": 1.127426266670227,
|
| 6904 |
+
"learning_rate": 9.933883934455038e-06,
|
| 6905 |
+
"loss": 0.035,
|
| 6906 |
+
"step": 9030
|
| 6907 |
+
},
|
| 6908 |
+
{
|
| 6909 |
+
"epoch": 8.472352389878163,
|
| 6910 |
+
"grad_norm": 0.7529722452163696,
|
| 6911 |
+
"learning_rate": 9.933810716220769e-06,
|
| 6912 |
+
"loss": 0.0303,
|
| 6913 |
+
"step": 9040
|
| 6914 |
+
},
|
| 6915 |
+
{
|
| 6916 |
+
"epoch": 8.481724461105905,
|
| 6917 |
+
"grad_norm": 0.6331318020820618,
|
| 6918 |
+
"learning_rate": 9.9337374979865e-06,
|
| 6919 |
+
"loss": 0.0301,
|
| 6920 |
+
"step": 9050
|
| 6921 |
+
},
|
| 6922 |
+
{
|
| 6923 |
+
"epoch": 8.491096532333646,
|
| 6924 |
+
"grad_norm": 0.9451204538345337,
|
| 6925 |
+
"learning_rate": 9.93366427975223e-06,
|
| 6926 |
+
"loss": 0.0301,
|
| 6927 |
+
"step": 9060
|
| 6928 |
+
},
|
| 6929 |
+
{
|
| 6930 |
+
"epoch": 8.500468603561387,
|
| 6931 |
+
"grad_norm": 1.0673385858535767,
|
| 6932 |
+
"learning_rate": 9.933591061517961e-06,
|
| 6933 |
+
"loss": 0.0311,
|
| 6934 |
+
"step": 9070
|
| 6935 |
+
},
|
| 6936 |
+
{
|
| 6937 |
+
"epoch": 8.509840674789128,
|
| 6938 |
+
"grad_norm": 0.5267199873924255,
|
| 6939 |
+
"learning_rate": 9.933517843283692e-06,
|
| 6940 |
+
"loss": 0.0258,
|
| 6941 |
+
"step": 9080
|
| 6942 |
+
},
|
| 6943 |
+
{
|
| 6944 |
+
"epoch": 8.51921274601687,
|
| 6945 |
+
"grad_norm": 1.0747129917144775,
|
| 6946 |
+
"learning_rate": 9.933444625049423e-06,
|
| 6947 |
+
"loss": 0.0308,
|
| 6948 |
+
"step": 9090
|
| 6949 |
+
},
|
| 6950 |
+
{
|
| 6951 |
+
"epoch": 8.52858481724461,
|
| 6952 |
+
"grad_norm": 0.5183865427970886,
|
| 6953 |
+
"learning_rate": 9.933371406815155e-06,
|
| 6954 |
+
"loss": 0.0272,
|
| 6955 |
+
"step": 9100
|
| 6956 |
+
},
|
| 6957 |
+
{
|
| 6958 |
+
"epoch": 8.537956888472353,
|
| 6959 |
+
"grad_norm": 0.8063677549362183,
|
| 6960 |
+
"learning_rate": 9.933298188580886e-06,
|
| 6961 |
+
"loss": 0.0256,
|
| 6962 |
+
"step": 9110
|
| 6963 |
+
},
|
| 6964 |
+
{
|
| 6965 |
+
"epoch": 8.547328959700094,
|
| 6966 |
+
"grad_norm": 0.7497850656509399,
|
| 6967 |
+
"learning_rate": 9.933224970346615e-06,
|
| 6968 |
+
"loss": 0.0272,
|
| 6969 |
+
"step": 9120
|
| 6970 |
+
},
|
| 6971 |
+
{
|
| 6972 |
+
"epoch": 8.556701030927835,
|
| 6973 |
+
"grad_norm": 1.4813112020492554,
|
| 6974 |
+
"learning_rate": 9.933151752112347e-06,
|
| 6975 |
+
"loss": 0.0271,
|
| 6976 |
+
"step": 9130
|
| 6977 |
+
},
|
| 6978 |
+
{
|
| 6979 |
+
"epoch": 8.566073102155576,
|
| 6980 |
+
"grad_norm": 0.9482595920562744,
|
| 6981 |
+
"learning_rate": 9.933078533878078e-06,
|
| 6982 |
+
"loss": 0.0256,
|
| 6983 |
+
"step": 9140
|
| 6984 |
+
},
|
| 6985 |
+
{
|
| 6986 |
+
"epoch": 8.575445173383319,
|
| 6987 |
+
"grad_norm": 0.5539655089378357,
|
| 6988 |
+
"learning_rate": 9.933005315643809e-06,
|
| 6989 |
+
"loss": 0.0274,
|
| 6990 |
+
"step": 9150
|
| 6991 |
+
},
|
| 6992 |
+
{
|
| 6993 |
+
"epoch": 8.58481724461106,
|
| 6994 |
+
"grad_norm": 0.7821139097213745,
|
| 6995 |
+
"learning_rate": 9.93293209740954e-06,
|
| 6996 |
+
"loss": 0.0284,
|
| 6997 |
+
"step": 9160
|
| 6998 |
+
},
|
| 6999 |
+
{
|
| 7000 |
+
"epoch": 8.5941893158388,
|
| 7001 |
+
"grad_norm": 0.9729026556015015,
|
| 7002 |
+
"learning_rate": 9.93285887917527e-06,
|
| 7003 |
+
"loss": 0.0256,
|
| 7004 |
+
"step": 9170
|
| 7005 |
+
},
|
| 7006 |
+
{
|
| 7007 |
+
"epoch": 8.603561387066541,
|
| 7008 |
+
"grad_norm": 1.1433371305465698,
|
| 7009 |
+
"learning_rate": 9.932785660941001e-06,
|
| 7010 |
+
"loss": 0.0274,
|
| 7011 |
+
"step": 9180
|
| 7012 |
+
},
|
| 7013 |
+
{
|
| 7014 |
+
"epoch": 8.612933458294282,
|
| 7015 |
+
"grad_norm": 1.211930751800537,
|
| 7016 |
+
"learning_rate": 9.932712442706732e-06,
|
| 7017 |
+
"loss": 0.0325,
|
| 7018 |
+
"step": 9190
|
| 7019 |
+
},
|
| 7020 |
+
{
|
| 7021 |
+
"epoch": 8.622305529522023,
|
| 7022 |
+
"grad_norm": 1.3734978437423706,
|
| 7023 |
+
"learning_rate": 9.932639224472463e-06,
|
| 7024 |
+
"loss": 0.0311,
|
| 7025 |
+
"step": 9200
|
| 7026 |
+
},
|
| 7027 |
+
{
|
| 7028 |
+
"epoch": 8.631677600749766,
|
| 7029 |
+
"grad_norm": 1.3476920127868652,
|
| 7030 |
+
"learning_rate": 9.932566006238195e-06,
|
| 7031 |
+
"loss": 0.0281,
|
| 7032 |
+
"step": 9210
|
| 7033 |
+
},
|
| 7034 |
+
{
|
| 7035 |
+
"epoch": 8.641049671977507,
|
| 7036 |
+
"grad_norm": 0.720197856426239,
|
| 7037 |
+
"learning_rate": 9.932492788003926e-06,
|
| 7038 |
+
"loss": 0.0233,
|
| 7039 |
+
"step": 9220
|
| 7040 |
+
},
|
| 7041 |
+
{
|
| 7042 |
+
"epoch": 8.650421743205248,
|
| 7043 |
+
"grad_norm": 1.2147605419158936,
|
| 7044 |
+
"learning_rate": 9.932419569769655e-06,
|
| 7045 |
+
"loss": 0.0308,
|
| 7046 |
+
"step": 9230
|
| 7047 |
+
},
|
| 7048 |
+
{
|
| 7049 |
+
"epoch": 8.65979381443299,
|
| 7050 |
+
"grad_norm": 0.5273356437683105,
|
| 7051 |
+
"learning_rate": 9.932346351535387e-06,
|
| 7052 |
+
"loss": 0.0278,
|
| 7053 |
+
"step": 9240
|
| 7054 |
+
},
|
| 7055 |
+
{
|
| 7056 |
+
"epoch": 8.669165885660732,
|
| 7057 |
+
"grad_norm": 1.316347360610962,
|
| 7058 |
+
"learning_rate": 9.932273133301118e-06,
|
| 7059 |
+
"loss": 0.0283,
|
| 7060 |
+
"step": 9250
|
| 7061 |
+
},
|
| 7062 |
+
{
|
| 7063 |
+
"epoch": 8.669165885660732,
|
| 7064 |
+
"eval_loss": 0.037036340683698654,
|
| 7065 |
+
"eval_pearson_cosine": 0.773975670337677,
|
| 7066 |
+
"eval_pearson_dot": 0.7285434007644653,
|
| 7067 |
+
"eval_pearson_euclidean": 0.7271639108657837,
|
| 7068 |
+
"eval_pearson_manhattan": 0.7293847799301147,
|
| 7069 |
+
"eval_runtime": 21.5505,
|
| 7070 |
+
"eval_samples_per_second": 69.604,
|
| 7071 |
+
"eval_spearman_cosine": 0.773229338598899,
|
| 7072 |
+
"eval_spearman_dot": 0.7297658810725091,
|
| 7073 |
+
"eval_spearman_euclidean": 0.7311555468063519,
|
| 7074 |
+
"eval_spearman_manhattan": 0.7331183382723726,
|
| 7075 |
+
"eval_steps_per_second": 8.724,
|
| 7076 |
+
"step": 9250
|
| 7077 |
+
},
|
| 7078 |
+
{
|
| 7079 |
+
"epoch": 8.678537956888473,
|
| 7080 |
+
"grad_norm": 0.6502562165260315,
|
| 7081 |
+
"learning_rate": 9.932199915066849e-06,
|
| 7082 |
+
"loss": 0.0255,
|
| 7083 |
+
"step": 9260
|
| 7084 |
+
},
|
| 7085 |
+
{
|
| 7086 |
+
"epoch": 8.687910028116214,
|
| 7087 |
+
"grad_norm": 1.172356128692627,
|
| 7088 |
+
"learning_rate": 9.93212669683258e-06,
|
| 7089 |
+
"loss": 0.0293,
|
| 7090 |
+
"step": 9270
|
| 7091 |
+
},
|
| 7092 |
+
{
|
| 7093 |
+
"epoch": 8.697282099343955,
|
| 7094 |
+
"grad_norm": 0.6329541206359863,
|
| 7095 |
+
"learning_rate": 9.932053478598312e-06,
|
| 7096 |
+
"loss": 0.0299,
|
| 7097 |
+
"step": 9280
|
| 7098 |
+
},
|
| 7099 |
+
{
|
| 7100 |
+
"epoch": 8.706654170571696,
|
| 7101 |
+
"grad_norm": 1.1246780157089233,
|
| 7102 |
+
"learning_rate": 9.931980260364041e-06,
|
| 7103 |
+
"loss": 0.0322,
|
| 7104 |
+
"step": 9290
|
| 7105 |
+
},
|
| 7106 |
+
{
|
| 7107 |
+
"epoch": 8.716026241799437,
|
| 7108 |
+
"grad_norm": 0.7996613383293152,
|
| 7109 |
+
"learning_rate": 9.931907042129772e-06,
|
| 7110 |
+
"loss": 0.0279,
|
| 7111 |
+
"step": 9300
|
| 7112 |
+
},
|
| 7113 |
+
{
|
| 7114 |
+
"epoch": 8.72539831302718,
|
| 7115 |
+
"grad_norm": 1.0772420167922974,
|
| 7116 |
+
"learning_rate": 9.931833823895504e-06,
|
| 7117 |
+
"loss": 0.0268,
|
| 7118 |
+
"step": 9310
|
| 7119 |
+
},
|
| 7120 |
+
{
|
| 7121 |
+
"epoch": 8.73477038425492,
|
| 7122 |
+
"grad_norm": 1.3459417819976807,
|
| 7123 |
+
"learning_rate": 9.931760605661235e-06,
|
| 7124 |
+
"loss": 0.0361,
|
| 7125 |
+
"step": 9320
|
| 7126 |
+
},
|
| 7127 |
+
{
|
| 7128 |
+
"epoch": 8.744142455482661,
|
| 7129 |
+
"grad_norm": 0.901692271232605,
|
| 7130 |
+
"learning_rate": 9.931687387426966e-06,
|
| 7131 |
+
"loss": 0.0317,
|
| 7132 |
+
"step": 9330
|
| 7133 |
+
},
|
| 7134 |
+
{
|
| 7135 |
+
"epoch": 8.753514526710402,
|
| 7136 |
+
"grad_norm": 1.1700392961502075,
|
| 7137 |
+
"learning_rate": 9.931614169192697e-06,
|
| 7138 |
+
"loss": 0.0257,
|
| 7139 |
+
"step": 9340
|
| 7140 |
+
},
|
| 7141 |
+
{
|
| 7142 |
+
"epoch": 8.762886597938145,
|
| 7143 |
+
"grad_norm": 1.1746001243591309,
|
| 7144 |
+
"learning_rate": 9.931540950958427e-06,
|
| 7145 |
+
"loss": 0.0261,
|
| 7146 |
+
"step": 9350
|
| 7147 |
+
},
|
| 7148 |
+
{
|
| 7149 |
+
"epoch": 8.772258669165886,
|
| 7150 |
+
"grad_norm": 1.250924825668335,
|
| 7151 |
+
"learning_rate": 9.931467732724158e-06,
|
| 7152 |
+
"loss": 0.0272,
|
| 7153 |
+
"step": 9360
|
| 7154 |
+
},
|
| 7155 |
+
{
|
| 7156 |
+
"epoch": 8.781630740393627,
|
| 7157 |
+
"grad_norm": 0.922290027141571,
|
| 7158 |
+
"learning_rate": 9.931394514489889e-06,
|
| 7159 |
+
"loss": 0.0295,
|
| 7160 |
+
"step": 9370
|
| 7161 |
+
},
|
| 7162 |
+
{
|
| 7163 |
+
"epoch": 8.791002811621368,
|
| 7164 |
+
"grad_norm": 0.6809844970703125,
|
| 7165 |
+
"learning_rate": 9.931321296255621e-06,
|
| 7166 |
+
"loss": 0.0269,
|
| 7167 |
+
"step": 9380
|
| 7168 |
+
},
|
| 7169 |
+
{
|
| 7170 |
+
"epoch": 8.800374882849109,
|
| 7171 |
+
"grad_norm": 0.8787119388580322,
|
| 7172 |
+
"learning_rate": 9.931248078021352e-06,
|
| 7173 |
+
"loss": 0.031,
|
| 7174 |
+
"step": 9390
|
| 7175 |
+
},
|
| 7176 |
+
{
|
| 7177 |
+
"epoch": 8.80974695407685,
|
| 7178 |
+
"grad_norm": 0.5186774134635925,
|
| 7179 |
+
"learning_rate": 9.931174859787083e-06,
|
| 7180 |
+
"loss": 0.0322,
|
| 7181 |
+
"step": 9400
|
| 7182 |
+
},
|
| 7183 |
+
{
|
| 7184 |
+
"epoch": 8.819119025304593,
|
| 7185 |
+
"grad_norm": 0.8100725412368774,
|
| 7186 |
+
"learning_rate": 9.931101641552814e-06,
|
| 7187 |
+
"loss": 0.026,
|
| 7188 |
+
"step": 9410
|
| 7189 |
+
},
|
| 7190 |
+
{
|
| 7191 |
+
"epoch": 8.828491096532334,
|
| 7192 |
+
"grad_norm": 0.7274125218391418,
|
| 7193 |
+
"learning_rate": 9.931028423318544e-06,
|
| 7194 |
+
"loss": 0.0291,
|
| 7195 |
+
"step": 9420
|
| 7196 |
+
},
|
| 7197 |
+
{
|
| 7198 |
+
"epoch": 8.837863167760075,
|
| 7199 |
+
"grad_norm": 1.1390098333358765,
|
| 7200 |
+
"learning_rate": 9.930955205084275e-06,
|
| 7201 |
+
"loss": 0.031,
|
| 7202 |
+
"step": 9430
|
| 7203 |
+
},
|
| 7204 |
+
{
|
| 7205 |
+
"epoch": 8.847235238987816,
|
| 7206 |
+
"grad_norm": 0.8184690475463867,
|
| 7207 |
+
"learning_rate": 9.930881986850006e-06,
|
| 7208 |
+
"loss": 0.0312,
|
| 7209 |
+
"step": 9440
|
| 7210 |
+
},
|
| 7211 |
+
{
|
| 7212 |
+
"epoch": 8.856607310215558,
|
| 7213 |
+
"grad_norm": 0.4963175356388092,
|
| 7214 |
+
"learning_rate": 9.930808768615737e-06,
|
| 7215 |
+
"loss": 0.0212,
|
| 7216 |
+
"step": 9450
|
| 7217 |
+
},
|
| 7218 |
+
{
|
| 7219 |
+
"epoch": 8.8659793814433,
|
| 7220 |
+
"grad_norm": 1.4110792875289917,
|
| 7221 |
+
"learning_rate": 9.930735550381467e-06,
|
| 7222 |
+
"loss": 0.0284,
|
| 7223 |
+
"step": 9460
|
| 7224 |
+
},
|
| 7225 |
+
{
|
| 7226 |
+
"epoch": 8.87535145267104,
|
| 7227 |
+
"grad_norm": 0.9356960654258728,
|
| 7228 |
+
"learning_rate": 9.930662332147198e-06,
|
| 7229 |
+
"loss": 0.0273,
|
| 7230 |
+
"step": 9470
|
| 7231 |
+
},
|
| 7232 |
+
{
|
| 7233 |
+
"epoch": 8.884723523898781,
|
| 7234 |
+
"grad_norm": 1.2740856409072876,
|
| 7235 |
+
"learning_rate": 9.930589113912929e-06,
|
| 7236 |
+
"loss": 0.0293,
|
| 7237 |
+
"step": 9480
|
| 7238 |
+
},
|
| 7239 |
+
{
|
| 7240 |
+
"epoch": 8.894095595126522,
|
| 7241 |
+
"grad_norm": 1.2273004055023193,
|
| 7242 |
+
"learning_rate": 9.930515895678661e-06,
|
| 7243 |
+
"loss": 0.0322,
|
| 7244 |
+
"step": 9490
|
| 7245 |
+
},
|
| 7246 |
+
{
|
| 7247 |
+
"epoch": 8.903467666354265,
|
| 7248 |
+
"grad_norm": 0.8036444187164307,
|
| 7249 |
+
"learning_rate": 9.930442677444392e-06,
|
| 7250 |
+
"loss": 0.0274,
|
| 7251 |
+
"step": 9500
|
| 7252 |
+
},
|
| 7253 |
+
{
|
| 7254 |
+
"epoch": 8.903467666354265,
|
| 7255 |
+
"eval_loss": 0.037216756492853165,
|
| 7256 |
+
"eval_pearson_cosine": 0.7742361426353455,
|
| 7257 |
+
"eval_pearson_dot": 0.7297594547271729,
|
| 7258 |
+
"eval_pearson_euclidean": 0.7265840172767639,
|
| 7259 |
+
"eval_pearson_manhattan": 0.7287671566009521,
|
| 7260 |
+
"eval_runtime": 27.1822,
|
| 7261 |
+
"eval_samples_per_second": 55.183,
|
| 7262 |
+
"eval_spearman_cosine": 0.773949198027488,
|
| 7263 |
+
"eval_spearman_dot": 0.7317025356234911,
|
| 7264 |
+
"eval_spearman_euclidean": 0.7328250947435205,
|
| 7265 |
+
"eval_spearman_manhattan": 0.7345883817446427,
|
| 7266 |
+
"eval_steps_per_second": 6.916,
|
| 7267 |
+
"step": 9500
|
| 7268 |
+
},
|
| 7269 |
+
{
|
| 7270 |
+
"epoch": 8.912839737582006,
|
| 7271 |
+
"grad_norm": 1.1801636219024658,
|
| 7272 |
+
"learning_rate": 9.930369459210123e-06,
|
| 7273 |
+
"loss": 0.0298,
|
| 7274 |
+
"step": 9510
|
| 7275 |
+
},
|
| 7276 |
+
{
|
| 7277 |
+
"epoch": 8.922211808809747,
|
| 7278 |
+
"grad_norm": 0.6167355179786682,
|
| 7279 |
+
"learning_rate": 9.930296240975853e-06,
|
| 7280 |
+
"loss": 0.0321,
|
| 7281 |
+
"step": 9520
|
| 7282 |
+
},
|
| 7283 |
+
{
|
| 7284 |
+
"epoch": 8.931583880037488,
|
| 7285 |
+
"grad_norm": 0.9813573956489563,
|
| 7286 |
+
"learning_rate": 9.930223022741584e-06,
|
| 7287 |
+
"loss": 0.0315,
|
| 7288 |
+
"step": 9530
|
| 7289 |
+
},
|
| 7290 |
+
{
|
| 7291 |
+
"epoch": 8.940955951265229,
|
| 7292 |
+
"grad_norm": 1.0033338069915771,
|
| 7293 |
+
"learning_rate": 9.930149804507315e-06,
|
| 7294 |
+
"loss": 0.0288,
|
| 7295 |
+
"step": 9540
|
| 7296 |
+
},
|
| 7297 |
+
{
|
| 7298 |
+
"epoch": 8.950328022492972,
|
| 7299 |
+
"grad_norm": 1.8989328145980835,
|
| 7300 |
+
"learning_rate": 9.930076586273046e-06,
|
| 7301 |
+
"loss": 0.0301,
|
| 7302 |
+
"step": 9550
|
| 7303 |
+
},
|
| 7304 |
+
{
|
| 7305 |
+
"epoch": 8.959700093720713,
|
| 7306 |
+
"grad_norm": 1.1895250082015991,
|
| 7307 |
+
"learning_rate": 9.930003368038778e-06,
|
| 7308 |
+
"loss": 0.0245,
|
| 7309 |
+
"step": 9560
|
| 7310 |
+
},
|
| 7311 |
+
{
|
| 7312 |
+
"epoch": 8.969072164948454,
|
| 7313 |
+
"grad_norm": 0.5209571719169617,
|
| 7314 |
+
"learning_rate": 9.929930149804509e-06,
|
| 7315 |
+
"loss": 0.0292,
|
| 7316 |
+
"step": 9570
|
| 7317 |
+
},
|
| 7318 |
+
{
|
| 7319 |
+
"epoch": 8.978444236176195,
|
| 7320 |
+
"grad_norm": 0.6561270952224731,
|
| 7321 |
+
"learning_rate": 9.929856931570238e-06,
|
| 7322 |
+
"loss": 0.0321,
|
| 7323 |
+
"step": 9580
|
| 7324 |
+
},
|
| 7325 |
+
{
|
| 7326 |
+
"epoch": 8.987816307403936,
|
| 7327 |
+
"grad_norm": 0.8421456217765808,
|
| 7328 |
+
"learning_rate": 9.92978371333597e-06,
|
| 7329 |
+
"loss": 0.0298,
|
| 7330 |
+
"step": 9590
|
| 7331 |
+
},
|
| 7332 |
+
{
|
| 7333 |
+
"epoch": 8.997188378631678,
|
| 7334 |
+
"grad_norm": 2.0356316566467285,
|
| 7335 |
+
"learning_rate": 9.929710495101701e-06,
|
| 7336 |
+
"loss": 0.0285,
|
| 7337 |
+
"step": 9600
|
| 7338 |
+
},
|
| 7339 |
+
{
|
| 7340 |
+
"epoch": 9.00656044985942,
|
| 7341 |
+
"grad_norm": 0.9041091799736023,
|
| 7342 |
+
"learning_rate": 9.929637276867432e-06,
|
| 7343 |
+
"loss": 0.0266,
|
| 7344 |
+
"step": 9610
|
| 7345 |
+
},
|
| 7346 |
+
{
|
| 7347 |
+
"epoch": 9.01593252108716,
|
| 7348 |
+
"grad_norm": 1.0879167318344116,
|
| 7349 |
+
"learning_rate": 9.929564058633163e-06,
|
| 7350 |
+
"loss": 0.0276,
|
| 7351 |
+
"step": 9620
|
| 7352 |
+
},
|
| 7353 |
+
{
|
| 7354 |
+
"epoch": 9.025304592314901,
|
| 7355 |
+
"grad_norm": 0.48896804451942444,
|
| 7356 |
+
"learning_rate": 9.929490840398893e-06,
|
| 7357 |
+
"loss": 0.0209,
|
| 7358 |
+
"step": 9630
|
| 7359 |
+
},
|
| 7360 |
+
{
|
| 7361 |
+
"epoch": 9.034676663542642,
|
| 7362 |
+
"grad_norm": 0.3795441687107086,
|
| 7363 |
+
"learning_rate": 9.929417622164624e-06,
|
| 7364 |
+
"loss": 0.0202,
|
| 7365 |
+
"step": 9640
|
| 7366 |
+
},
|
| 7367 |
+
{
|
| 7368 |
+
"epoch": 9.044048734770385,
|
| 7369 |
+
"grad_norm": 0.6517238020896912,
|
| 7370 |
+
"learning_rate": 9.929344403930355e-06,
|
| 7371 |
+
"loss": 0.0258,
|
| 7372 |
+
"step": 9650
|
| 7373 |
+
},
|
| 7374 |
+
{
|
| 7375 |
+
"epoch": 9.053420805998126,
|
| 7376 |
+
"grad_norm": 0.7814950942993164,
|
| 7377 |
+
"learning_rate": 9.929271185696087e-06,
|
| 7378 |
+
"loss": 0.0217,
|
| 7379 |
+
"step": 9660
|
| 7380 |
+
},
|
| 7381 |
+
{
|
| 7382 |
+
"epoch": 9.062792877225867,
|
| 7383 |
+
"grad_norm": 0.8012738823890686,
|
| 7384 |
+
"learning_rate": 9.929197967461818e-06,
|
| 7385 |
+
"loss": 0.0187,
|
| 7386 |
+
"step": 9670
|
| 7387 |
+
},
|
| 7388 |
+
{
|
| 7389 |
+
"epoch": 9.072164948453608,
|
| 7390 |
+
"grad_norm": 0.9685556292533875,
|
| 7391 |
+
"learning_rate": 9.929124749227549e-06,
|
| 7392 |
+
"loss": 0.0223,
|
| 7393 |
+
"step": 9680
|
| 7394 |
+
},
|
| 7395 |
+
{
|
| 7396 |
+
"epoch": 9.081537019681349,
|
| 7397 |
+
"grad_norm": 0.8415644764900208,
|
| 7398 |
+
"learning_rate": 9.92905153099328e-06,
|
| 7399 |
+
"loss": 0.0174,
|
| 7400 |
+
"step": 9690
|
| 7401 |
+
},
|
| 7402 |
+
{
|
| 7403 |
+
"epoch": 9.090909090909092,
|
| 7404 |
+
"grad_norm": 0.5449099540710449,
|
| 7405 |
+
"learning_rate": 9.92897831275901e-06,
|
| 7406 |
+
"loss": 0.025,
|
| 7407 |
+
"step": 9700
|
| 7408 |
+
},
|
| 7409 |
+
{
|
| 7410 |
+
"epoch": 9.100281162136833,
|
| 7411 |
+
"grad_norm": 0.7209439873695374,
|
| 7412 |
+
"learning_rate": 9.928905094524741e-06,
|
| 7413 |
+
"loss": 0.0221,
|
| 7414 |
+
"step": 9710
|
| 7415 |
+
},
|
| 7416 |
+
{
|
| 7417 |
+
"epoch": 9.109653233364574,
|
| 7418 |
+
"grad_norm": 0.5441991090774536,
|
| 7419 |
+
"learning_rate": 9.928831876290472e-06,
|
| 7420 |
+
"loss": 0.0217,
|
| 7421 |
+
"step": 9720
|
| 7422 |
+
},
|
| 7423 |
+
{
|
| 7424 |
+
"epoch": 9.119025304592315,
|
| 7425 |
+
"grad_norm": 0.7726917862892151,
|
| 7426 |
+
"learning_rate": 9.928758658056203e-06,
|
| 7427 |
+
"loss": 0.0264,
|
| 7428 |
+
"step": 9730
|
| 7429 |
+
},
|
| 7430 |
+
{
|
| 7431 |
+
"epoch": 9.128397375820056,
|
| 7432 |
+
"grad_norm": 1.4641560316085815,
|
| 7433 |
+
"learning_rate": 9.928685439821935e-06,
|
| 7434 |
+
"loss": 0.0215,
|
| 7435 |
+
"step": 9740
|
| 7436 |
+
},
|
| 7437 |
+
{
|
| 7438 |
+
"epoch": 9.137769447047798,
|
| 7439 |
+
"grad_norm": 0.7165714502334595,
|
| 7440 |
+
"learning_rate": 9.928612221587664e-06,
|
| 7441 |
+
"loss": 0.025,
|
| 7442 |
+
"step": 9750
|
| 7443 |
+
},
|
| 7444 |
+
{
|
| 7445 |
+
"epoch": 9.137769447047798,
|
| 7446 |
+
"eval_loss": 0.03766760975122452,
|
| 7447 |
+
"eval_pearson_cosine": 0.7719284296035767,
|
| 7448 |
+
"eval_pearson_dot": 0.7294802665710449,
|
| 7449 |
+
"eval_pearson_euclidean": 0.7313249111175537,
|
| 7450 |
+
"eval_pearson_manhattan": 0.7333976626396179,
|
| 7451 |
+
"eval_runtime": 27.8656,
|
| 7452 |
+
"eval_samples_per_second": 53.83,
|
| 7453 |
+
"eval_spearman_cosine": 0.7718354415047185,
|
| 7454 |
+
"eval_spearman_dot": 0.730941479257979,
|
| 7455 |
+
"eval_spearman_euclidean": 0.7371740495785648,
|
| 7456 |
+
"eval_spearman_manhattan": 0.7388595895844299,
|
| 7457 |
+
"eval_steps_per_second": 6.747,
|
| 7458 |
+
"step": 9750
|
| 7459 |
+
},
|
| 7460 |
+
{
|
| 7461 |
+
"epoch": 9.14714151827554,
|
| 7462 |
+
"grad_norm": 1.162800908088684,
|
| 7463 |
+
"learning_rate": 9.928539003353395e-06,
|
| 7464 |
+
"loss": 0.0299,
|
| 7465 |
+
"step": 9760
|
| 7466 |
+
},
|
| 7467 |
+
{
|
| 7468 |
+
"epoch": 9.15651358950328,
|
| 7469 |
+
"grad_norm": 0.826000452041626,
|
| 7470 |
+
"learning_rate": 9.928465785119127e-06,
|
| 7471 |
+
"loss": 0.0204,
|
| 7472 |
+
"step": 9770
|
| 7473 |
+
},
|
| 7474 |
+
{
|
| 7475 |
+
"epoch": 9.165885660731021,
|
| 7476 |
+
"grad_norm": 0.4205090403556824,
|
| 7477 |
+
"learning_rate": 9.928392566884858e-06,
|
| 7478 |
+
"loss": 0.0213,
|
| 7479 |
+
"step": 9780
|
| 7480 |
+
},
|
| 7481 |
+
{
|
| 7482 |
+
"epoch": 9.175257731958762,
|
| 7483 |
+
"grad_norm": 1.4229509830474854,
|
| 7484 |
+
"learning_rate": 9.928319348650589e-06,
|
| 7485 |
+
"loss": 0.0232,
|
| 7486 |
+
"step": 9790
|
| 7487 |
+
},
|
| 7488 |
+
{
|
| 7489 |
+
"epoch": 9.184629803186505,
|
| 7490 |
+
"grad_norm": 0.550862729549408,
|
| 7491 |
+
"learning_rate": 9.92824613041632e-06,
|
| 7492 |
+
"loss": 0.0247,
|
| 7493 |
+
"step": 9800
|
| 7494 |
+
},
|
| 7495 |
+
{
|
| 7496 |
+
"epoch": 9.194001874414246,
|
| 7497 |
+
"grad_norm": 0.6965065598487854,
|
| 7498 |
+
"learning_rate": 9.92817291218205e-06,
|
| 7499 |
+
"loss": 0.025,
|
| 7500 |
+
"step": 9810
|
| 7501 |
+
},
|
| 7502 |
+
{
|
| 7503 |
+
"epoch": 9.203373945641987,
|
| 7504 |
+
"grad_norm": 0.43077608942985535,
|
| 7505 |
+
"learning_rate": 9.928099693947781e-06,
|
| 7506 |
+
"loss": 0.0251,
|
| 7507 |
+
"step": 9820
|
| 7508 |
+
},
|
| 7509 |
+
{
|
| 7510 |
+
"epoch": 9.212746016869728,
|
| 7511 |
+
"grad_norm": 0.450005441904068,
|
| 7512 |
+
"learning_rate": 9.928026475713512e-06,
|
| 7513 |
+
"loss": 0.0212,
|
| 7514 |
+
"step": 9830
|
| 7515 |
+
},
|
| 7516 |
+
{
|
| 7517 |
+
"epoch": 9.222118088097469,
|
| 7518 |
+
"grad_norm": 1.184260368347168,
|
| 7519 |
+
"learning_rate": 9.927953257479244e-06,
|
| 7520 |
+
"loss": 0.0222,
|
| 7521 |
+
"step": 9840
|
| 7522 |
+
},
|
| 7523 |
+
{
|
| 7524 |
+
"epoch": 9.231490159325212,
|
| 7525 |
+
"grad_norm": 0.5146024823188782,
|
| 7526 |
+
"learning_rate": 9.927880039244975e-06,
|
| 7527 |
+
"loss": 0.0237,
|
| 7528 |
+
"step": 9850
|
| 7529 |
+
},
|
| 7530 |
+
{
|
| 7531 |
+
"epoch": 9.240862230552953,
|
| 7532 |
+
"grad_norm": 0.638936460018158,
|
| 7533 |
+
"learning_rate": 9.927806821010704e-06,
|
| 7534 |
+
"loss": 0.0313,
|
| 7535 |
+
"step": 9860
|
| 7536 |
+
},
|
| 7537 |
+
{
|
| 7538 |
+
"epoch": 9.250234301780694,
|
| 7539 |
+
"grad_norm": 0.5175133943557739,
|
| 7540 |
+
"learning_rate": 9.927733602776437e-06,
|
| 7541 |
+
"loss": 0.0267,
|
| 7542 |
+
"step": 9870
|
| 7543 |
+
},
|
| 7544 |
+
{
|
| 7545 |
+
"epoch": 9.259606373008435,
|
| 7546 |
+
"grad_norm": 0.46744242310523987,
|
| 7547 |
+
"learning_rate": 9.927660384542167e-06,
|
| 7548 |
+
"loss": 0.0221,
|
| 7549 |
+
"step": 9880
|
| 7550 |
+
},
|
| 7551 |
+
{
|
| 7552 |
+
"epoch": 9.268978444236176,
|
| 7553 |
+
"grad_norm": 1.0883630514144897,
|
| 7554 |
+
"learning_rate": 9.927587166307898e-06,
|
| 7555 |
+
"loss": 0.0209,
|
| 7556 |
+
"step": 9890
|
| 7557 |
+
},
|
| 7558 |
+
{
|
| 7559 |
+
"epoch": 9.278350515463918,
|
| 7560 |
+
"grad_norm": 0.8785117864608765,
|
| 7561 |
+
"learning_rate": 9.927513948073629e-06,
|
| 7562 |
+
"loss": 0.0243,
|
| 7563 |
+
"step": 9900
|
| 7564 |
+
},
|
| 7565 |
+
{
|
| 7566 |
+
"epoch": 9.28772258669166,
|
| 7567 |
+
"grad_norm": 1.33463716506958,
|
| 7568 |
+
"learning_rate": 9.927440729839361e-06,
|
| 7569 |
+
"loss": 0.0231,
|
| 7570 |
+
"step": 9910
|
| 7571 |
+
},
|
| 7572 |
+
{
|
| 7573 |
+
"epoch": 9.2970946579194,
|
| 7574 |
+
"grad_norm": 0.6693497896194458,
|
| 7575 |
+
"learning_rate": 9.92736751160509e-06,
|
| 7576 |
+
"loss": 0.0205,
|
| 7577 |
+
"step": 9920
|
| 7578 |
+
},
|
| 7579 |
+
{
|
| 7580 |
+
"epoch": 9.306466729147141,
|
| 7581 |
+
"grad_norm": 0.44432297348976135,
|
| 7582 |
+
"learning_rate": 9.927294293370821e-06,
|
| 7583 |
+
"loss": 0.0255,
|
| 7584 |
+
"step": 9930
|
| 7585 |
+
},
|
| 7586 |
+
{
|
| 7587 |
+
"epoch": 9.315838800374882,
|
| 7588 |
+
"grad_norm": 0.9900962710380554,
|
| 7589 |
+
"learning_rate": 9.927221075136553e-06,
|
| 7590 |
+
"loss": 0.0262,
|
| 7591 |
+
"step": 9940
|
| 7592 |
+
},
|
| 7593 |
+
{
|
| 7594 |
+
"epoch": 9.325210871602625,
|
| 7595 |
+
"grad_norm": 0.8196175694465637,
|
| 7596 |
+
"learning_rate": 9.927147856902284e-06,
|
| 7597 |
+
"loss": 0.0262,
|
| 7598 |
+
"step": 9950
|
| 7599 |
+
},
|
| 7600 |
+
{
|
| 7601 |
+
"epoch": 9.334582942830366,
|
| 7602 |
+
"grad_norm": 1.0177077054977417,
|
| 7603 |
+
"learning_rate": 9.927074638668015e-06,
|
| 7604 |
+
"loss": 0.0267,
|
| 7605 |
+
"step": 9960
|
| 7606 |
+
},
|
| 7607 |
+
{
|
| 7608 |
+
"epoch": 9.343955014058107,
|
| 7609 |
+
"grad_norm": 1.218307375907898,
|
| 7610 |
+
"learning_rate": 9.927001420433746e-06,
|
| 7611 |
+
"loss": 0.0248,
|
| 7612 |
+
"step": 9970
|
| 7613 |
+
},
|
| 7614 |
+
{
|
| 7615 |
+
"epoch": 9.353327085285848,
|
| 7616 |
+
"grad_norm": 0.9856002926826477,
|
| 7617 |
+
"learning_rate": 9.926928202199476e-06,
|
| 7618 |
+
"loss": 0.0233,
|
| 7619 |
+
"step": 9980
|
| 7620 |
+
},
|
| 7621 |
+
{
|
| 7622 |
+
"epoch": 9.362699156513589,
|
| 7623 |
+
"grad_norm": 0.6501719355583191,
|
| 7624 |
+
"learning_rate": 9.926854983965207e-06,
|
| 7625 |
+
"loss": 0.0271,
|
| 7626 |
+
"step": 9990
|
| 7627 |
+
},
|
| 7628 |
+
{
|
| 7629 |
+
"epoch": 9.372071227741332,
|
| 7630 |
+
"grad_norm": 0.5562245845794678,
|
| 7631 |
+
"learning_rate": 9.926781765730938e-06,
|
| 7632 |
+
"loss": 0.031,
|
| 7633 |
+
"step": 10000
|
| 7634 |
+
},
|
| 7635 |
+
{
|
| 7636 |
+
"epoch": 9.372071227741332,
|
| 7637 |
+
"eval_loss": 0.03722027316689491,
|
| 7638 |
+
"eval_pearson_cosine": 0.7733820676803589,
|
| 7639 |
+
"eval_pearson_dot": 0.725334644317627,
|
| 7640 |
+
"eval_pearson_euclidean": 0.7356694936752319,
|
| 7641 |
+
"eval_pearson_manhattan": 0.7372510433197021,
|
| 7642 |
+
"eval_runtime": 25.8635,
|
| 7643 |
+
"eval_samples_per_second": 57.997,
|
| 7644 |
+
"eval_spearman_cosine": 0.7735257400299028,
|
| 7645 |
+
"eval_spearman_dot": 0.726586040502744,
|
| 7646 |
+
"eval_spearman_euclidean": 0.7407176416099474,
|
| 7647 |
+
"eval_spearman_manhattan": 0.7421316928799319,
|
| 7648 |
+
"eval_steps_per_second": 7.269,
|
| 7649 |
+
"step": 10000
|
| 7650 |
}
|
| 7651 |
],
|
| 7652 |
"logging_steps": 10,
|